Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4901. Min Act: -0.0000

Data Index: 881717 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1124310 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3820. Min Act: -0.0000

Data Index: 663072 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1862556 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4072. Min Act: -0.0000

Data Index: 317649 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1907989 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3933. Min Act: -0.0000

Data Index: 414061 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4083. Min Act: -0.0000

Data Index: 828344 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4892. Min Act: -0.0000

Data Index: 676250 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.5125. Min Act: -0.0000

Data Index: 505721 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1822892 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3394. Min Act: -0.0000

Data Index: 1680567 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4118. Min Act: -0.0000

Data Index: 92198 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3282. Min Act: -0.0000

Data Index: 297297 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1495833 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3474. Min Act: -0.0000

Data Index: 308037 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.0654. Min Act: -0.0000

Data Index: 252264 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3441. Min Act: -0.0000

Data Index: 625790 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1935425 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1927768 (The Pile)

Max Activating Token Index: 276